kavyamanohar/Malasar_Luke
This model is a fine-tuned version of openai/whisper-small on the Spoken Bible Corpus: Malasar dataset. It achieves the following results on the evaluation set:
- Loss: 0.6056
- Wer: 58.9377
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1635 | 11.36 | 250 | 0.3183 | 63.2210 |
| 0.0134 | 22.73 | 500 | 0.4616 | 63.7350 |
| 0.0023 | 34.09 | 750 | 0.5199 | 59.6802 |
| 0.0004 | 45.45 | 1000 | 0.5627 | 58.5951 |
| 0.0003 | 56.82 | 1250 | 0.5831 | 59.0520 |
| 0.0002 | 68.18 | 1500 | 0.5959 | 58.9949 |
| 0.0002 | 79.55 | 1750 | 0.6032 | 59.1091 |
| 0.0002 | 90.91 | 2000 | 0.6056 | 58.9377 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.15.0